First-Stage Prostate Cancer Identification on Histopathological Images: Hand-Driven versus Automatic Learning.

First-Stage Prostate Cancer Identification on Histopathological Images: Hand-Driven versus Automatic Learning.
复制标题

DOI:
10.3390/e21040356
复制
发表时间:
2019-04-02
期刊:
Entropy (Basel, Switzerland)
影响因子:
--
通讯作者:
Naranjo V
Naranjo V
中科院分区:
其他
文献类型:
--
作者:
García G;Colomer A;Naranjo V

文献摘要

参考文献

被引文献

相似文献

组织病理学图像分析是识别前列腺癌最可靠的方法。大多数研究试图开发计算机辅助系统来面对格里森分级问题。相反,我们深入研究了健康和癌组织之间的歧视在其最早的阶段,只专注于包含在自动分割的腺体候选人的信息。我们提出了一种手动驱动的学习方法,在该方法中,我们执行一个详尽的手工特征提取阶段,以一种新的方式结合描述符的形态,纹理,分形和上下文信息的候选人正在研究。然后,我们进行深入的统计分析,以选择构成优化机器学习分类器输入的最相关特征。此外,我们首次应用于前列腺分割腺体,深度学习算法修改了流行的VGG19神经网络。我们微调了架构的最后一个卷积块,以提供关于腺体图像的模型特定知识。手动驱动的学习方法,使用非线性支持向量机,报告了一个轻微的优于其余的实验,最终多类的准确性,在假腺体(文物),良性腺体和格里森3级腺体之间的歧视。
Analysis of histopathological image supposes the most reliable procedure to identify prostate cancer. Most studies try to develop computer aid-systems to face the Gleason grading problem. On the contrary, we delve into the discrimination between healthy and cancerous tissues in its earliest stage, only focusing on the information contained in the automatically segmented gland candidates. We propose a hand-driven learning approach, in which we perform an exhaustive hand-crafted feature extraction stage combining in a novel way descriptors of morphology, texture, fractals and contextual information of the candidates under study. Then, we carry out an in-depth statistical analysis to select the most relevant features that constitute the inputs to the optimised machine-learning classifiers. Additionally, we apply for the first time on prostate segmented glands, deep-learning algorithms modifying the popular VGG19 neural network. We fine-tuned the last convolutional block of the architecture to provide the model specific knowledge about the gland images. The hand-driven learning approach, using a nonlinear Support Vector Machine, reports a slight outperforming over the rest of experiments with a final multi-class accuracy of in the discrimination between false glands (artefacts), benign glands and Gleason grade 3 glands.
DOI: 10.1109/tip.2010.2044957
发表时间: 2010-06-01
影响因子: 10.6
作者:
Guo, Zhenhua;Zhang, Lei;Zhang, David
通讯作者: Zhang, David
DOI: 10.1109/tmi.2009.2012704
发表时间: 2009-07-01
影响因子: 10.6
作者:
Huang, Po-Whei;Lee, Cheng-Hsiung
通讯作者: Lee, Cheng-Hsiung
DOI: 10.1038/s41598-018-33026-5
发表时间: 2018-10-08
期刊: Scientific reports
影响因子: 4.6
作者:
Leo P;Elliott R;Shih NNC;Gupta S;Feldman M;Madabhushi A
通讯作者: Madabhushi A
DOI: 10.1038/s41598-018-30535-1
发表时间: 2018-08-13
期刊: SCIENTIFIC REPORTS
影响因子: 4.6
作者:
Arvaniti, Eirini;Fricker, Kim S.;Claassen, Manfred
通讯作者: Claassen, Manfred
DOI: 10.1109/tpami.2006.132
发表时间: 2006-07-01
影响因子: 23.6
作者:
Beare, R
通讯作者: Beare, R